{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.2557544757033248,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005115089514066497,
      "grad_norm": NaN,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.005115089514066497,
      "eval_loss": NaN,
      "eval_runtime": 24.3768,
      "eval_samples_per_second": 13.537,
      "eval_steps_per_second": 1.723,
      "step": 1
    },
    {
      "epoch": 0.010230179028132993,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.015345268542199489,
      "grad_norm": NaN,
      "learning_rate": 1.5e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.020460358056265986,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.02557544757033248,
      "grad_norm": NaN,
      "learning_rate": 2.5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.030690537084398978,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.03580562659846547,
      "grad_norm": NaN,
      "learning_rate": 3.5e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.04092071611253197,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.04603580562659847,
      "grad_norm": NaN,
      "learning_rate": 4.5e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.05115089514066496,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.056265984654731455,
      "grad_norm": NaN,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.061381074168797956,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.06649616368286446,
      "grad_norm": NaN,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.07161125319693094,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.07672634271099744,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.08184143222506395,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": NaN,
      "learning_rate": 8.5e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.09207161125319693,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.09718670076726342,
      "grad_norm": NaN,
      "learning_rate": 9.5e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.10230179028132992,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.10741687979539642,
      "grad_norm": NaN,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.11253196930946291,
      "grad_norm": NaN,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.12276214833759591,
      "grad_norm": NaN,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.1278772378516624,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.1278772378516624,
      "eval_loss": NaN,
      "eval_runtime": 24.2316,
      "eval_samples_per_second": 13.619,
      "eval_steps_per_second": 1.733,
      "step": 25
    },
    {
      "epoch": 0.1329923273657289,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.13810741687979539,
      "grad_norm": NaN,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.1432225063938619,
      "grad_norm": NaN,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.1483375959079284,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.1534526854219949,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.1585677749360614,
      "grad_norm": NaN,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.1636828644501279,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.16879795396419436,
      "grad_norm": NaN,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": NaN,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.17902813299232737,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.18414322250639387,
      "grad_norm": NaN,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.18925831202046037,
      "grad_norm": NaN,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.19437340153452684,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.19948849104859334,
      "grad_norm": NaN,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.20460358056265984,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.20971867007672634,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.21483375959079284,
      "grad_norm": NaN,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.21994884910485935,
      "grad_norm": NaN,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.22506393861892582,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.23017902813299232,
      "grad_norm": NaN,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": NaN,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.24040920716112532,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.24552429667519182,
      "grad_norm": NaN,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.2506393861892583,
      "grad_norm": NaN,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.2557544757033248,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.2557544757033248,
      "eval_loss": NaN,
      "eval_runtime": 24.2345,
      "eval_samples_per_second": 13.617,
      "eval_steps_per_second": 1.733,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.54256789372928e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}